Search

Vegetables are good sources to meet the needs for protein, vitamins, minerals for human. One of popular choices for vegetables in Indonesia is Pak Choy (Bassica rapa). Good quality vegetables is usually identified by the color and the shape of the leaves. Therefore an automatic system to detect the quality of the leaves is needed. In this paper, we propose a proper method to detect the quality of the Pak Choy leaves using machine learning. Monitoring the quality of Pak Choy leaves with the naked eye is usually conducted based on the color of the leaves. The healthy leaves are usually characterized by green color while the unhealthy leaves are usually have a green color with the yellow spot. Based on these observations, we develop the system using color intensity features such as RGB and HSI and Support Vector Machine (SVM) as the classifiers. Our system achieves accuracy of 92.5% using linear kernels.

Rapid and accurate detection of malaria infection lead to better treatment for the patients. It can help in reducing the mortality due to the illness. We analyze the effectiveness of using several color-spaces, i.e., RGB, HSV, YC b C r , CIELAB, and grayscale in the Color Cascading Framework. Since each color space consists of several color channels, it is necessary to choose the right color channel to be used as the object of analysis so that the best system performance can be obtained. We propose measurements on each color channel by using a measurement of pixel intensity homogeneity using entropy method. From the experimental results, it was found that the color channel entropy value shows a direct relationship with the accuracy of the system. The highest color channel entropy value corresponded to the best accuracy value. The results of testing on each color-space revealed that the most suitable color channel for Color Cascading Framework was a Green color channel from RGB color-space, with performance accuracy, specificity, and sensitivity are 98.26%, 97.91%, and 98.61% respectively.

The developed application allows to have consolidated graphic information of people with disabilities that are located in potential risk areas such as Cotopaxi Volcano. The information is indicated in real time on georeferenced maps and details the person (names, age, sex), the location of the dwelling, type of disability. This information is valuable and ends the realization of the location of these people, you can meet the evacuation plans that has been planned. The development of the application is based on its operation and applications such as Google Maps and assisted GPS, allowing additionally the visualization of the lahares area, the area of greatest danger, the areas of shelters and evacuation routes, shelters or secure sites in the Cities of Latacunga and Sangolqui. If the user wants to see the information of the person with a disability or visually know which person has a higher and more serious disability than others, he / she should simply differentiate the colors of the georeferenced points that are on the map, the red color indicates a And the green color indicates a percentage between 50% and 74%, the orange color indicates a percentage between 40% and 49%, the celestial color indicates a percentage between 30% and 39% and the purple color indicates A percentage between 1% and 29% or senior citizens. In the case, it is desired to evacuate the disabled person is pressed at the georeferenced point and automatically opens a new window with the route generated to reach the chosen place avoiding crossing the danger zone.

Two-channel tunable white lighting (TWL) systems represent the next wave of solid-state lighting (SSL) systems and promise flexibility in light environment while maintaining the high reliability and luminous efficacy expected with SSL devices. TWL systems utilize LED assemblies consisting of two different LED spectra (i.e., often a warm white assembly and a cool white assembly) that are integrated into modules. While these systems provide the ability to adjust the lighting spectrum to match the physiology needs of the task at hand, they also are a potentially more complex lighting system from a performance and reliability perspective. We report an initial study on the reliability performance of such lighting systems including an examination of the lumen maintenance and chromaticity stability of warm white and cool white LED assemblies and the multi-channel driver that provides power to the assemblies. Accelerated stress tests including operational bake tests conducted at 75°C and 95°C were used to age the LED modules, while more aggressive temperature and humidity tests were used for the drivers in this study. Small differences in the performance between the two LED assemblies were found and can be attributed to the different phosphor chemistries. The lumen maintenances of both LED assemblies were excellent. The warm white LED assemblies were found to shift slightly in the green color direction over time while the cool white LED assemblies shifted slightly in the yellow color direction. The net result of these chromaticity shifts is a small, barely perceptible reduction in the tuning range after 6,000 hours of exposure to an accelerating elevated temperature of 75°C.

In this paper, the measurement of pressure gauge using color segmentation is proposed for the safety management of fire extinguisher. The main idea is that pressure gauge includes a green color indicating the normal pressure. In order to measure the fire extinguisher pressure, the proposed algorithm consists of two steps. The first step is performed the image cropping to find the region of the pressure gauge using CHT algorithm and green detection. The next step is calculated to find the indicator needle of the pressure gauge using the color code pattern around the green area. Finally, the actual pressure value is calculated based on the angle of the green area and the indicating needle. Some experimental results are conducted so as to verify the proposed algorithm, and the proposed method calculated the actual pressure, effectively.

Image processing techniques on digital systems which are used on agriculture can be evaluated for different aims. For instance; detection of wild herb, to estimate product, to determine ripeness and quality are some of them. The most widely used one is detection of fruits-vegetables. Particularly such image processing techniques are needed for robotic applications in agriculture. For example, identify and locating the fruit/vegetable is a major problem for the collection of fruit/vegetable by a robot. In this work, the aim is to determine the locations of orange and green color fruits, to separate from the leaves and branches in the area.

The remote measurement of the heart rate while the user is watching TV can bring many promising applications to our home such as user's preference estimation, automatic digest edition and fitness. We developed a non-contact heart rate measurement method using camera image so that users can measure the heart rate without any attachments. We focused attention on the blood oxygenated hemoglobin which absorbs the green light and measures the heart rate by detecting the variation of the green color intensity of a person's face image. In previous research, it was not possible to measure the heart rate with precision when a person was in movement. In this proposed method, we can expect that it will be applied to various applications since we can accurately measure the heart rate even while moving the face. The results showed a performance of detection error smaller than 3 bpm for lightning conditions over 500 lux and distances up to 6.0 m.

In nature occur complex processes phenomena that are difficult to quantify and analyze quickly by humans. Processes that require the application of computational methods to streamline and automate processing events that occur consistently, in this sense, the application of computer vision methods in different fields as biology, medicine, agriculture and others. The paper presents the analysis of images using computer vision techniques applied to study the variation of size and color variation in fruit ripening. The images reveal that changes occur in shades of color during the ripening period, variations of the colors that go from green to yellow. The analyzes show that the fruits rapidly lost in the early days the size and lose their green color after being separated from the plant. The loss of size is a situation that should demand attention from producers and marketers of fruit because it involves the loss of size weight loss. In understanding the results takes into account the principles and physiological maturation process. The study was performed with fruit ripening Lulo, Solanum sp; the track size variation is performed for 25 days doing image capture every 15 minutes 24 hours.

The objective of this study is to map Cyanobacteria Bloom in brackish Lakes Shinji and Nakaumi using satellite data such as MODIS. The 10 satellite sensor data such as QuickBird, ALOS AVNIR-2, and MODIS from November to December, 2010 were collected in these lakes. Cyanobacteria bloom was distinguished by viewing from satellite data. Furthermore, it was judged quantitatively by Rayleigh corrected reflectance of 500 m spatial resolution MODIS. As a result, Green Color Index (G/[R+G+B]) was found to be suitable for mapping of Cyanobacteria Bloom.

Based on CIE 1976 L*a*b* uniform color space, L*, a*, b* of jadeite-jade, emerald and turquoise were considered as independent variable, then color green of Jadeite-Jade could be distinguished from other two gemstones with discriminant analysis. Three gemstones discriminant functions were given by the fisher analysis. But in order to reduce false rate 22.9% from turquoise and 7.4% from emerald, green color of three gemstones were reclassified into 6 species by K-Means cluster analysis, and then 6 new discriminant functions were calculated to examine the validity of cluster analysis, finally the linear discriminant function model with high accuracy rate 98.8% were erected from fisher discriminant analysis.

About 8% of men are affected by color blindness. That population is at a disadvantage since they cannot perceive a substantial amount of the visual information. This work presents two computational tools developed to assist color blind people. The first one tests color blindness and assess its severity. The second tool is based on Fuzzy Logic, and implements a method proposed to simulate real red and green color blindness in order to generate synthetic cases of color vision disturbance in a statistically significant amount. Our purpose is to develop correction tools and obtain a deeper understanding of the accessibility problems faced by people with chromatic visual impairment.

A green-color AC electroluminescent device with ZnS:TbOF thin films has been fabricated by diode RF-sputtering. The effect of oxygen doping and sputtering conditions on the device performance has been investigated. It has been found that the performance improvement can be achieved by codoping oxygen into the active layers. >